{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SK4MJSGSIMCJT4J6GO4PZTLUUI","short_pith_number":"pith:SK4MJSGS","schema_version":"1.0","canonical_sha256":"92b8c4c8d2430499f13e33b8fccd74a20cb4b1dff6ea943d1ae5b8c687c5ba83","source":{"kind":"arxiv","id":"2506.14965","version":1},"attestation_state":"computed","paper":{"title":"Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Abulhair Saparov, Chengqian Gao, Eric P. Xing, Fan Zhou, Feng Yao, Haonan Li, Jianshu She, Kun Zhou, Mikhail Yurochkin, Nilabjo Dey, Richard Fan, Shibo Hao, Taylor W. Killian, Tianyang Liu, Yi Gu, Yonghao Zhuang, Yuan Li, Yuexin Bian, Yuheng Zha, Yuqi Wang, Yutao Xie, Zhengzhong Liu, Zhiting Hu, Zhoujun Cheng","submitted_at":"2025-06-17T20:24:00Z","abstract_excerpt":"Reinforcement learning (RL) has emerged as a promising approach to improve large language model (LLM) reasoning, yet most open efforts focus narrowly on math and code, limiting our understanding of its broader applicability to general reasoning. A key challenge lies in the lack of reliable, scalable RL reward signals across diverse reasoning domains. We introduce Guru, a curated RL reasoning corpus of 92K verifiable examples spanning six reasoning domains--Math, Code, Science, Logic, Simulation, and Tabular--each built through domain-specific reward design, deduplication, and filtering to ensu"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.14965","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T20:24:00Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"d9e7df69ede1c36759e16c28ad25dd148fd27e040809d47e361d08cd5252141c","abstract_canon_sha256":"57718cc0c5c586ba67136c35a18809a2d88d8f4918cd6f35403caffe4490e3a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:34.915308Z","signature_b64":"JsYr+YeT6ViJKLZ+sRM0il+w1c2PpR5zMR9YEAD/+JZYoUvLD1e2+DZy7SMdErsSvS5uxj0mFLJ/nKS+wJZUBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92b8c4c8d2430499f13e33b8fccd74a20cb4b1dff6ea943d1ae5b8c687c5ba83","last_reissued_at":"2026-07-05T11:23:34.914810Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:34.914810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Abulhair Saparov, Chengqian Gao, Eric P. Xing, Fan Zhou, Feng Yao, Haonan Li, Jianshu She, Kun Zhou, Mikhail Yurochkin, Nilabjo Dey, Richard Fan, Shibo Hao, Taylor W. Killian, Tianyang Liu, Yi Gu, Yonghao Zhuang, Yuan Li, Yuexin Bian, Yuheng Zha, Yuqi Wang, Yutao Xie, Zhengzhong Liu, Zhiting Hu, Zhoujun Cheng","submitted_at":"2025-06-17T20:24:00Z","abstract_excerpt":"Reinforcement learning (RL) has emerged as a promising approach to improve large language model (LLM) reasoning, yet most open efforts focus narrowly on math and code, limiting our understanding of its broader applicability to general reasoning. A key challenge lies in the lack of reliable, scalable RL reward signals across diverse reasoning domains. We introduce Guru, a curated RL reasoning corpus of 92K verifiable examples spanning six reasoning domains--Math, Code, Science, Logic, Simulation, and Tabular--each built through domain-specific reward design, deduplication, and filtering to ensu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14965","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.14965/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.14965","created_at":"2026-07-05T11:23:34.914868+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.14965v1","created_at":"2026-07-05T11:23:34.914868+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14965","created_at":"2026-07-05T11:23:34.914868+00:00"},{"alias_kind":"pith_short_12","alias_value":"SK4MJSGSIMCJ","created_at":"2026-07-05T11:23:34.914868+00:00"},{"alias_kind":"pith_short_16","alias_value":"SK4MJSGSIMCJT4J6","created_at":"2026-07-05T11:23:34.914868+00:00"},{"alias_kind":"pith_short_8","alias_value":"SK4MJSGS","created_at":"2026-07-05T11:23:34.914868+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20008","citing_title":"VIMPO: Value-Implicit Policy Optimization for LLMs","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00609","citing_title":"CARE-RL: Capability-Aware Reinforcement Learning for Mitigating Cross-Domain Conflicts","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18089","citing_title":"From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2507.01679","citing_title":"Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2509.08827","citing_title":"A Survey of Reinforcement Learning for Large Reasoning Models","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2503.09567","citing_title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","ref_index":127,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09748","citing_title":"Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SK4MJSGSIMCJT4J6GO4PZTLUUI","json":"https://pith.science/pith/SK4MJSGSIMCJT4J6GO4PZTLUUI.json","graph_json":"https://pith.science/api/pith-number/SK4MJSGSIMCJT4J6GO4PZTLUUI/graph.json","events_json":"https://pith.science/api/pith-number/SK4MJSGSIMCJT4J6GO4PZTLUUI/events.json","paper":"https://pith.science/paper/SK4MJSGS"},"agent_actions":{"view_html":"https://pith.science/pith/SK4MJSGSIMCJT4J6GO4PZTLUUI","download_json":"https://pith.science/pith/SK4MJSGSIMCJT4J6GO4PZTLUUI.json","view_paper":"https://pith.science/paper/SK4MJSGS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.14965&json=true","fetch_graph":"https://pith.science/api/pith-number/SK4MJSGSIMCJT4J6GO4PZTLUUI/graph.json","fetch_events":"https://pith.science/api/pith-number/SK4MJSGSIMCJT4J6GO4PZTLUUI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SK4MJSGSIMCJT4J6GO4PZTLUUI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SK4MJSGSIMCJT4J6GO4PZTLUUI/action/storage_attestation","attest_author":"https://pith.science/pith/SK4MJSGSIMCJT4J6GO4PZTLUUI/action/author_attestation","sign_citation":"https://pith.science/pith/SK4MJSGSIMCJT4J6GO4PZTLUUI/action/citation_signature","submit_replication":"https://pith.science/pith/SK4MJSGSIMCJT4J6GO4PZTLUUI/action/replication_record"}},"created_at":"2026-07-05T11:23:34.914868+00:00","updated_at":"2026-07-05T11:23:34.914868+00:00"}